Discover AI Agent Skills

Drop a video and describe the caption look you're going for — bold neon subtitles for a gaming reel, clean minimal text for a corporate explainer, or animated pop captions for a TikTok. This ai-video-caption-style skill analyzes your footage and applies styled, timed captions that feel intentional, not slapped on. Choose fonts, colors, positioning, and animation behavior through plain language prompts. Supports mp4, mov, avi, webm, and mkv files. Built for creators, marketers, and educators who want captions that actually look good.

End-to-end leadership change signal composite. Takes any set of companies, detects recent leadership changes (new VP+, C-suite hires and promotions), evaluates relevance to your product, and drafts personalized outreach. Uses Apollo People Search (free) for fast detection + Apollo Enrichment (1 credit/person) for employment history, start dates, LinkedIn URLs, and verified emails.

Diagnose interface errors, drops, CRCs, duplex mismatches, flapping, speed negotiation issues, and counter trends on routers, switches, and Linux hosts. Use when an interface shows errors, drops, CRCs, flapping, or a duplex or speed mismatch.

使用SMTP发送带附件的邮件，支持HTML模板、多收件人和文件附件。基于nodemailer。

基于预设 URL 列表抓取内容，筛选高质量技术信息并生成每日 Markdown 报告。

协作写简体中文长文，侧重公众号。用于“写篇文章”“整理成文”或“改这篇草稿”。

Receive and verify Intercom webhooks. Use when setting up Intercom webhook handlers, debugging X-Hub-Signature verification, or handling customer messaging events like conversation.user.created, conversation.admin.replied, contact.user.created, or ticket.created.

139 proven marketing ideas organized by category with implementation guidance. Use when asked for marketing ideas, growth strategies, campaign brainstorms, or "what should I do to grow." Trigger phrases: "marketing ideas", "growth ideas", "how to grow", "marketing strategies", "campaign ideas", "promote my product", "marketing brainstorm", "growth tactics", "what should I try", "marketing playbook".

Customer success across onboarding, adoption, retention, and expansion. Use when designing onboarding playbooks, calculating health scores, building QBR decks, planning renewal strategies, or identifying expansion opportunities.

Automatically fetches up-to-date documentation from Context7 when users ask about libraries, frameworks, APIs, or need code examples. Triggers proactively without explicit user request.

Audit Lightning Web Components for SLDS design-system compliance and produce a scored quality report. Runs the SLDS linter and analyzes CSS for theming hook usage and pairing, scoring SLDS findings across categories into an overall grade. Use when asked to "score my component's SLDS", "SLDS scorecard", "SLDS quality report", "audit SLDS compliance", "how good is my SLDS", "check SLDS quality", "rate my SLDS styling", "evaluate my component's SLDS", "is this component's SLDS ready to ship?", "look at my LWC for SLDS issues", "audit SLDS before I submit", "review my component's SLDS before code review", or any time a user wants an SLDS quality assessment or SLDS production-readiness check on an LWC. Not for fixing violations (use design-systems-slds2-migrate), building new components (use design-systems-slds-apply), or accessibility/WCAG/ARIA audits (use experience-accessibility-validate).

Render views and templates in Phoenix using HEEx templates, function components, slots, and assigns

Use when you need to apply Java concurrency best practices — including thread safety fundamentals, ExecutorService thread pool management, concurrent design patterns like Producer-Consumer, asynchronous programming with CompletableFuture, immutability and safe publication, deadlock avoidance, virtual threads, structured concurrency, scoped values, backpressure, cancellation discipline, and observability for concurrent systems. This should trigger for requests such as Review Java code for concurrency; Review Java code for thread safety; Fix race conditions in Java concurrency code; Choose ExecutorService or virtual threads in Java; Improve synchronization and shared mutable state handling; Apply structured concurrency for related Java subtasks. Part of Plinth Toolkit

Profile construction data to understand characteristics, distributions, quality metrics, and patterns. Essential for data quality assessment and ETL planning.

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

Execute a complete tax-loss harvesting workflow from candidate identification through post-harvest monitoring. Use when the user asks about finding TLH candidates, gain/loss budgeting, replacement security selection, wash-sale compliance, or harvest execution planning. Also trigger when users mention 'unrealized losses in my portfolio', 'swap ETFs for tax purposes', 'harvest losses before year-end', 'substantially identical security', 'wash-sale window', 'NIIT offset', 'loss carryforward', or ask how much tax they can save by harvesting.

Compares two app bundles to identify size changes, new or removed artifacts, and platform differences. Can be invoked with bundle IDs, dashboard URLs, or branch names.

Build microservices - Spring Cloud, service mesh, event-driven, resilience patterns